Agent skill
env-update-secrets
Use when updating environment secrets like GITHUB_TOKEN, NPM_TOKEN, or API keys on the user's machine
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/env-update-secrets
SKILL.md
Updating Environment Secrets
Location
All secrets live in: ~/.config/fish/config.secrets.fish
This file is sourced by ~/.config/fish/config.fish on shell startup.
Format
export VAR_NAME='value'
Current Secrets
| Variable | Purpose |
|---|---|
GITHUB_TOKEN |
GitHub CLI and API authentication |
NPM_TOKEN |
npm registry authentication |
NPM_PUBLISH_TOKEN |
npm package publishing |
Workflow
- Read
~/.config/fish/config.secrets.fish - Edit the relevant
exportline with new value - Tell user to reload:
source ~/.config/fish/config.fish
Adding New Secrets
Add new export lines to the same file. Keep secrets consolidated here rather than scattered across dotfiles.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?